© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 696
    Prev
    Next
    INDEX
    Explanations

    database-related terms and identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.31
    1:0.06
    2:0.09
    3:0.08
    4:0.04
    5:0.06
    6:0.07
    7:0.02
    8:0.05
    9:0.05
    10:0.06
    11:0.05
    Negative Logits
     Canaveral
    -1.90
     Dund
    -1.82
     Stockholm
    -1.79
     Kamp
    -1.64
     Swedish
    -1.63
    aturdays
    -1.51
     Sorce
    -1.49
     Eugene
    -1.48
     Canberra
    -1.46
    inav
    -1.45
    POSITIVE LOGITS
    ]
    3.15
    ]"
    2.98
    }.
    2.97
    ]."
    2.95
    ],
    2.88
    ].
    2.83
    ']
    2.81
    ]'
    2.81
    ]:
    2.78
    }
    2.75
    Activations Density 0.002%

    No Known Activations